Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Descriptions and opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Any
    -0.07
     three
    -0.07
    4
    -0.07
     certifications
    -0.07
    олит
    -0.06
    6
    -0.06
     african
    -0.06
     These
    -0.06
     Two
    -0.06
     zda
    -0.06
    POSITIVE LOGITS
    Crud
    0.07
    __↵
    0.07
     çıkış
    0.06
    .WriteHeader
    0.06
     모습
    0.06
    \">"
    0.06
     дів
    0.06
     advisers
    0.06
     Schw
    0.06
     Refriger
    0.06
    Act Density 0.126%

    No Known Activations